ABSTRACT
Traditional cross-language similarity assessment techniques mostly rely on the theories of linguistics and pragmatics, which is also bound up with the natural features of "natural language". This paper mainly studies the similarity comparison algorithm of "blank" concept in Chinese and Western poetics under the background of Internet. In this paper, a sentence-level cross-language similarity assessment framework (SCLSE) is proposed. The framework is based on word embedding as the underlying vector representation, which is used to learn the semantic representation of sentences through the fusion of various neural network structures, and finally outputs the similarity score of sentences. In this paper, we also divide the short text into paragraphs and treat the paragraphs as long sentences as sequence input to realize the iterative calculation of similarity on a larger scale. In this paper, we set up different comparative experiments to verify the effectiveness and application value of SCLSE framework in the cross-language text similarity assessment task under different text unit granularity.
- Vij S, Tayal D, Jain A . A Machine Learning Approach for Automated Evaluation of Short Answers Using Text Similarity Based on WordNet Graphs. Wireless Personal Communications, 2020, 111(2):1271-1282.Google ScholarCross Ref
- Kong L, Han Z, Qi H , A Ranking-Based Text Matching Approach for Plagiarism Detection. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, 2018, E101.A(5):799-810.Google ScholarCross Ref
- Qian J, He Z . Mainlobe interference suppression with eigenprojection algorithm and similarity constraints. Electronics Letters, 2016, 52(3):228-230.Google ScholarCross Ref
- Huang W, Xiao X, Xu M. Design and implementation of domain-specific cognitive system based on question similarity algorithm. Cognitive Systems Research, 2019, 57(OCT.):20-24.Google ScholarDigital Library
- Su L, Huang Y, Gibeaut J , The index array approach and the dual tiled similarity algorithm for UAS hyper-spatial image processing. GeoInformatica, 2016, 20(4):859-878.Google ScholarDigital Library
- Peng, Li, Hong, Similarity Search Algorithm over Data Supply Chain Based on Key Points. Tsinghua Science and Technology, 2017, 02(v.22):58-68.Google Scholar
- Arboleda F, Ramos J , Rendon J. A Characteristic-Based Similarity Algorithm for Finding Similar Users in a Social Network. Journal of current issues in media and t, 2016, 8(2):139-154.Google Scholar
- Chen S, Cao S, Wang H, Post-stack seismic data interpolation using a fast non-local similarity matching algorithm. Studia Geophysica et Geodaetica, 2021, 65(1):1-12.Google ScholarCross Ref
- Zhou Y, Deng Y, J Xie, EPAS: A Sampling Based Similarity Identification Algorithm for the Cloud. Cloud Computing, IEEE Transactions on, 2018, 6(3):720-733.Google Scholar
- Chen S, Cao S, Wang H , Post-stack seismic data interpolation using a fast non-local similarity matching algorithm. Studia Geophysica et Geodaetica, 2021, 65(1):1-12.Google ScholarCross Ref
- A Comparative Algorithm of the Similarity in “Blank” Concept for Chinese and Western Poetics in the Context of Internet
Recommendations
Similarity computation of low-frequency Chinese words
FSKD'09: Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1This paper proposes a novel method on Chinese low-frequency word similarity computation. It adopts a combinational strategy to compute word similarity, which exploits dictionary Hownet and constructed corpus retrieved from Internet. It has 3 steps: (1) ...
Similarity Computation of Low-frequency Chinese Words
FSKD '09: Proceedings of the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 01This paper proposes a novel method on Chinese low-frequency word similarity computation. It adopts a combinational strategy to compute word similarity, which exploits dictionary Hownet and constructed corpus retrieved from Internet. It has 3 steps: (1) ...
The Semantic Computing Model of Sentence Similarity Based on Chinese FrameNet
WI-IAT '09: Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 03The semantic similarity computing among sentences is important in many fields of NLP. This paper proposes a sentence similarity theory based on Chinese Dependency Graph (CDG) from Chinese FrameNet (CFN). Firstly, the CFN project is introduced, and then ...
Comments